US20020141660A1 - Document scanner, system and method - Google Patents

Document scanner, system and method Download PDF

Info

Publication number
US20020141660A1
US20020141660A1 US09804272 US80427201A US2002141660A1 US 20020141660 A1 US20020141660 A1 US 20020141660A1 US 09804272 US09804272 US 09804272 US 80427201 A US80427201 A US 80427201A US 2002141660 A1 US2002141660 A1 US 2002141660A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
data
field
document
system
decoded
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US09804272
Other versions
US6782144B2 (en )
Inventor
Jorge Bellavita
Jorge Pucci
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Multiscan Corp
Original Assignee
Multiscan Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/2054Selective acquisition/locating/processing of specific regions, e.g. highlighted text, fiducial marks, predetermined fields, document type identification
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K2209/00Indexing scheme relating to methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K2209/01Character recognition

Abstract

The document scanner, system and method operates in conjunction with a document imprinted with data and a plurality of form documents adapted to have data imprinted thereon. The documents have at least one and typically many data image fields. Ultimately, the document scanner, system and method outputs a delimited string of decoded characters to another computer system via a common computer communications port. The method includes either scanning a form document to obtain positional information of the data field or fields or inputting a topological description of the field. Typically, the operator identifies descriptors for each data field which include data field size information, data type information, the presence or absence of data validation parameters, the presence or absence of data error reporting and data correction routines or parameters, and data output destination information. The data output destination information locates the decoded data in a certain sequence or location in the delimited string of decoded characters output to the coupled computer system. The document scanner, system and method scans the document imprinted with data and captures an image thereof. The scanned input document image is compared with the stored forms, and particularly the stored data field descriptors utilizing positional, data field size and data type information. The system selects one of the stored forms, extracts the data from each data field, decodes or calculates the data, and validates the data (in the presence of data validation parameters) and stores the decoded/calculated data. A data error reporting and data correction system, activated in the presence of the data error reporting and correction descriptor, enables correction of errors.

Description

  • The present invention relates to a document scanner for scanning, locating and deciphering data in data fields on one or more documents imprinted with data, a computer system therefor and a method therefor. [0001]
  • Although document scanners are relatively widely available (those scanners obtaining an image of a document) and there are computer software programs which read the information from the scanned image of the document and decipher and extract information from the document (such as OCR or optical character reader programs), there is a need for a stand alone, computer based unit which scans a document imprinted with data, locates the data on the document, deciphers the data and outputs the data in a common format to other computer systems. [0002]
  • U.S. Pat. No. 5,499,108 to Cotte et al. discloses a Document-Driven Scanning Input Device which communicates with a computer via an RS232 interface. Col. [0003] 4, line 54. In FIG. 12, and beginning at col. 10, line 29, Cotte '108 discloses the use of an input device 214 which sends information codes via an RS232 cable to host computer 210. In one embodiment, the host computer 210 recognizes the codes generated by input device 214 and processes the information in accordance with the code. This processing may include faxing the scanned image, sending the image in an e-mail message or performing word processing on the image. Col. 10, line 47, line 48, and line 54. In an alternate embodiment (col. 10, line 54), input device 214 analyzes the data stream from the scanned document to locate the code on the document. In one embodiment, the code on the document is a special symbol which input device 214 recognizes. Col. 11, lines 24-30. A graphic symbol may be used. Col. 11, lines 34-35. The input device 214 may be trained with symbol recognition software to recognize a particular symbol. Col. 11, lines 44-46. Predefined or predetermined graphic signals can be printed on the document to be scanned. Col. 11, lines 53-55. FIGS. 26-28 show graphic symbols identified in a “hot zone” or data field. These graphic symbols are recognized by input device 214. Particularly, reference point 406 provides an index point for the symbol recognition and the recognition software captures data commands in hot zone 404 (FIG. 26) or hot zone 404 in (FIG. 27) or hot zone 410 in FIG. 28. See col. 12, lines 5-20.
  • Cotte '108 also discloses the use of a preprinted document form for each type of operation. Col. [0004] 13, lines 26-28. Hand drawn symbols are also recognized by input device 214. Col. 13, lines 38-42. “FIG. 16 represents the classes of embodiments where the command symbols 243 and 245 are placed either in hot zone which are not on the top of the page or randomly placed on the page. Recognition of symbols where random placement on the page is practiced is more easily performed when formalized symbols or stickers are used which the recognition software has already been trained to recognize.” Col. 13, lines 54-61. After the input device 214 recognizes the symbol, the input device then compares the captured command and compares it to a list of previously stored symbols in order to decode the command. Col. 14, lines 7-12. Hence, Cotte '108 decodes the scanned data field. “The input device software then generates the appropriate commands to send to the host software package invoked by the command symbol to cause the host software so invoked to appropriately process the data received from the input device.” Col. 14, lines 30-34.
  • Cotte '108 describes FIG. 13A as obtaining a scanned image data which is compressed by the input device. Col. [0005] 14, line 52. FIG. 13B is described at col. 15, lines 8-55 as a routine wherein the input device scans the document, generates a command to the host computer and the user on the host computer then selects a menu option for that scanned image. Cotte '108 seems to output the scanned item as an image file rather than as a data file.
  • U.S. Pat. No. 5,243,149 to Comerford et al. discloses a Method and Apparatus for Improving the Paper Interface to Computing Systems. The two major components utilized in Comerford '149 include a digitizing tablet [0006] 10 and a hand held scanner 15. See FIGS. 1-2; Col. 5, lines 9-13. The document is scanned and stored in an ordinary manner. Col. 7, lines 7-12. A control document is also prepared such that the control document links the scanned document file with other files such as an annotation file. The scanned image files and the files containing electronic representation of handwritten notes (an annotation file) are processed at a work station after being downloaded from the notepad to the work station. The analysis is conducted with a character recognition software and with handwriting recognition software. Col. 9, lines 7-20.
  • U.S. Pat. No. 5,392,447 to Schlack et al. discloses an Image-Based Electronic Pocket Organizer with Integral Scanning. In this computerized pocket organizer or personal data assistant, the operator interacts with the computer system through a touch sensitive electronic display panel [0007] 14 based upon various overlay screens or windows. The operator interacts with the windows by touching the screen to perform various functions such as data entry, hand printed text entry, virtual alpha numeric keyboard operations, organizer navigational operations, among others. Col. 3, lines 60-69. After a document is scanned, the electronic file is processed by an optical character recognition system or a photo or image processing system. Col. 6, lines 48-57. To process business cards, the business card is scanned by the scanning unit and character recognition software is applied to this electronic scanned image data to identify the text information therein. Col. 8, lines 37-44. A relational database is utilized to link various information and certain data fields. However, with respect to the input of business card information, the operator is prompted at the initiation of the scanned operation to identify and attach a file tag containing one or more of the linking fields to the image being scanned. In this manner, each scanned image can be easily identified and cross-referenced with tagged data files. Col. 9, lines 51-62. With respect to medical insurance information which is scanned directly from the patient's medical card, the system performs a text identification routine (OCR) on the image bit map of the scanned medical card to identify areas of the bit map that contain text information. “A box is drawn around each of the areas that are determined to contain text information.” The system then decodes the image and extracts text information in the box. “The operator can then transfer the identified text data within selected boxes into the text information file by touching a selected box to fill in a template field that is overlayed on the display. The template field continues to prompt the user to select a box for each of the fields in the text information file.” Col. 10, lines 26-43.
  • U.S. Pat. No. 6,134,338 to Solberg et al. discloses a Computer System for Converting Documents Bearing Symbols and Alphanumeric Text. Solberg '338 states that it is particularly well suited to converting a raster image of a scanned hard copy source document bearing a drawing view of the three dimensional object, symbols and alphanumeric text relating to height, width, length, depth and angle of edges of the three dimensional object into mathematically accurate vector computer drawing files which files are based on the symbols in alphanumeric text scanned from the source document. The automated system includes the use of commercially available text recognition software for automatic conversion of raster text, including handwritten, upper and lower case text, and rotated text into AUTO CAD text strings. Col. [0008] 15, lines 47-52. The disclose states that after alphanumeric text has been recognized, the user can edit the resulting ASCII text as necessary. The preset optical character recognition parameters can automatically subject questionable text recognitions to user review. Col. 27, lines 55-59. In step 4.3 (FIG. 1A), alphanumeric text 180 and floating viewport 242 is recognized. Col. 28, lines 6-8. If necessary, the user can edit the text to correct OCR recognition errors. Col. 28, lines 12-14. In step 4.3 and 4.4, the OCR program creates a text file obtained from the scanned document. Col. 29, lines 57-60. See also FIG. 2 and step 4.
  • U.S. Pat. No. 5,970,170 to Kadashevich et al. discloses a Character Recognition System for Scanned and Real Time Handwritten Characters. The disclosure in the Kadashevich '170 relates to detecting and decoding handwritten characters including an image processor connecting to a document scanner which receives the scanned image of a previously created document and generating one or more ordered cluster arrays. These ordered cluster arrays contain spatially ordered coordinate arrays of skeletal image arcs representing handwritten characters. The handwritten characters are processed using several techniques. Kadashevich '170 does not seem to show the use of applying one of a plurality of forms to a scanned image, extracting data based on the forms and the scanned image, validating the data and that outputting the data is a delimited file. [0009]
  • The prior references do not show a single, computerized, unitary device which scans a number of documents imprinted with data, compares each document to previously stored form documents, selects one of the form documents, lifts or extracts the data from the input document having imprinted data thereon, and decodes that data based upon previously stored data characteristics. Further, the prior art devices do not show, in a single, unitary, computer system, extracting the data from the document having imprinted data thereon without regard to orientation of the input document and outputting the decoded data as a delimited string of characters or a delimited data field. [0010]
  • OBJECTS OF THE INVENTION
  • It is an object of the present invention to provide a document scanner and a system and a method which enables the user to scan a document imprinted with data, extract that data based upon a match between the scanned document and a plurality of form documents, decode the data, disregard misalignment or smudges on the input document image, and output decoded data as a delimited string of decoded characters to a further computerized device via a common computer communications link, all encompassed within a single computerized machine or system. [0011]
  • It is another object of the present invention to provide a document scanner, a system and a method wherein the operator can easily scan a form document, locate the important data fields on that scanned form document, size the data image field, identify data type for that data field, identify the presence or absence of any data validation parameters, identify the presence or absence of any data error reporting and data correction routines or parameters, and identify a data output destination for that decoded data in a delimited string of decoded characters output to a further computer device. [0012]
  • It is another object of the present invention to provide an operator interface for the identification of data field descriptors, those descriptors including positional information for the data field, data field size, data type, data validation, error reporting and correction, and data output destination information. [0013]
  • It is an additional object of the present invention to incorporate the scanning, operator input, identification and storing of data field descriptors, comparison of scanned document image with a plurality of forms, selection of one of the forms, extraction data from a data field, decoding and validating that data, reporting and correcting the data and outputting the decoded data all in a single, stand alone, unitary, computerized system. [0014]
  • SUMMARY OF THE INVENTION
  • The document scanner, system and method operates in conjunction with a document imprinted with data and a plurality of form documents adapted to have data imprinted thereon. The form document or documents have at least one data image field. Typically, the form document has many data image fields. Ultimately, the document scanner, system and method outputs a delimited string of decoded characters to another computer system via a common computer communications link such as a serial, ethernet, USB, SCSI, parallel interface, etc. The method includes either scanning a form document to obtain positional information of the data field on the form document or inputting topological description for the data image field for the form document. The topological description includes at least positional information for the data field. Typically the operator, in conjunction with an operator interface, identifies data field descriptors for each data field. The data field descriptors include data field size information, data type information, the presence or absence of data validation parameters, the presence or absence of data error reporting and data correction routines or parameters, and data output destination information. The data output destination information locates the decoded data in a certain sequence location in the delimited string of decoded characters output to the further computer system. The document scanner, system and method scans the document imprinted with data and captures an image thereof. The scanned input document image is compared with the stored forms, and particularly the stored data field descriptors utilizing positional, data field size and data type information. The system selects one of the stored forms corresponding to the scanned image. The document scanner, system and method then extracts the data from the scanned image based upon positional information for each data field, decodes the information based upon the data field descriptors, and validates the data (in the presence of data validation parameters) and stores the decoded data. A data error reporting and data correction system, activated in the presence of the data error reporting and correction descriptor, enables the operator to correct any errors ascertained from the extracted and decoded data from the data image fields. The document scanner, system and method outputs, via a compiler, the decoded data as part of the delimited string of decoded characters based upon the data output destination information. The scanner, system and method also includes a deskewing routine which accommodates and corrects for any misalignment in the initially scanned input document with respect to the positional information for each data image field. Further, the system includes a noise reduction system which attenuates smudges or imperfections in the data fields.[0015]
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • Further objects and advantages of the present invention can be found in the detailed description of the preferred embodiment when taken in conjunction with the accompanying drawings in which: [0016]
  • FIG. 1 diagrammatically illustrates the document scanner as both a system chart and as a data processing method; [0017]
  • FIG. 2 diagrammatically and graphically illustrates scanning a form document thereby enabling the operator to identify and store data field descriptors for the form document; and [0018]
  • FIG. 3 diagrammatically illustrates the major processing steps for scanning an input document imprinted with data, locating the data, deciphering the data, and outputting the data as a delimited string of decoded characters. [0019]
  • DETAIL DESCRIPTION OF THE PREFERRED EMBODIMENT
  • The present invention relates to a document scanner, system and a method for scanning a document (sometimes called herein “an input document”) imprinted with data, locating the data on the input document, deciphering the data, and outputting the decoded data as a delimited string of decoded characters to a further computer system via a common computer communications link. [0020]
  • FIG. 1 diagrammatically shows the unitary, stand alone computerized system [0021] 10 and also shows the data flow and processing method for data from the input document. The input document is fed into scanner system 10 as noted by arrow 12 and the ultimate output from scanner system 10 is noted by arrow 15 which output is applied to a common computer communications link or port. Further computerized devices (not shown) are coupled to output port 15. Output port 15 may be configured as shown below.
    Output Port Options
    Serial
    Ethernet
    USB
    SCSI
    Parallel
    Etc.
  • In addition as an option, document scanner [0022] 10 can output the scanned image of the input document at port 17. Ports 15 and 17 may be coupled together to form a single port.
  • The major functional blocks, embodied in both hardware and software in document scanner [0023] 10, are illustrated in FIG. 1. Initially, the input document (which can also be a form document) is handled and processed via digitalization unit 20. The other functional units include form processing unit 40, data processing unit 60, control unit 80, and a user interface system 82. User interface system 82 includes display 84, keyboard 86 and pointer device 88 (for example, a mouse, track ball, etc.).
  • Digitalization unit [0024] 20 includes hardware and operative software to provide automatic document feeder and scanning mechanism 22 for the input document. The document feeder and scanning mechanism 22 works under the supervision of feed control, double and chain feed detection 24. The output of automatic document feeder and scanning mechanism is applied to the deskewing and noise reduction module 26. After deskewing and noise reduction (to eliminate misalignment of the scanned image and smudges and imperfections from the scanned input document), the system realigns the scanned image via image registering function 28. The output of deskewing and noise reduction module 26 is fed to the optional image output 34 to optionally provide an output to the optional image output port 17.
  • Optionally, an optional imprinting module [0025] 30 can print on the scanned documents while they are being processed by the automatic document feeder and scanning mechanism 22 and before they reach the paper out stage 32.
  • Form processing unit [0026] 40 maintains a forms database 42 in a computer memory. The forms database provides input to form detector module 44 and field extraction module 46 operates on data fields or data field images in the scanned input document. The output from field extraction module 46 is applied field recognition module 48. Form processing unit 40 includes recognition engines 50. These recognition engines enable the system to match and decode extracted data images from the data fields based upon standardized data formats.
  • Document scanner [0027] 10 can recognize the following data in the positionally located data fields.
  • Coded Data Table
  • printed letters or numbers [0028]
  • optical marks, ticks, cross-outs (OMR) [0029]
  • handwritten numbers or letters (ICR) [0030]
  • bar codes (linear and 2D) (BCR) [0031]
  • special characters (MICR, OCR-A, OCR-B, F-13B, CMC 7) [0032]
  • MICR is typically magnetic and character recognition formulas (see generally, U.S. Pat. No. 6,183,148); E13B is a font character set established as a standard in certain industries (see generally U.S. Pat. No. 5,729,621); ICR is intelligent character recognition, numeral American and/or European style, which is read either in either free position or in character boxes (for example, see ICR generally in U.S. Pat. No. 5,970,171); OMR represents multiple types of optical marks such as X, tick mark, non-solid hatching marks all of which can be decoded in free positioning fields; and bar code recognition is provided for the following: code [0033] 39, code bar, code 2 of 5, code 12 of 5, code 128, UCC 128, code 93, UPC A, UPC E, EAN, Posnet, PDF 417, DATA MATRIX, AZTEC, etc., all in free positions or selected orientation positions.
  • The output for form processing unit [0034] 40 is applied to data processing unit 60. Data processing unit 60 includes data field and interfield rule checker or validator 62 which accepts input from, as necessary, dictionary module 64, mathematics check algorithm 66, logical check algorithm 68 or a semantic rule validator module. Field rule checker and validator 62 may generate an error report send via control unit 80 to display 84. Manual correction is enabled via operator assistance and user interface 82 into a summation or substitution module 65. The output of summation unit 65 is applied to data formatting unit 67. The data formatting unit compiles the decoded data, places the scanned, decoded corrected data and/or calculated data based on rules and decoded data into the proper location in the delimited string of decoded characters output to the further computer system (not shown) via common communications port 15. Optical marks may be calculated based upon known industry standards or formulas. Calculated data is processed in a similar manner as compared with decoded data and the terms, in a general sense, are similar.
  • FIG. 2 diagrammatically and graphically illustrates the form input system and process flow. There are two mechanisms which the operator may utilize to input form document information into computer system scanner [0035] 10. In one methodology, a form document is scanned by scanner system 10. The form document may or may not have imprinted data thereon. The other methodology involves an operator inputting topological descriptions for the data image field into the system. Data is extracted from data fields that are positionally located on an input form document 110. The following Data Field Description Table shows typical data field descriptors for each data field.
  • Data Field Description
  • positional information [0036]
  • data field size [0037]
  • type of data (or types of data) in field [0038]
  • data properties parameters (dictionary logical check, logical rules, mathematic rules, semantic rules) [0039]
  • error routine and data correction input/output [0040]
  • destination of decoded or calculated data in output file [0041]
  • The input form document, in the illustrated embodiment in FIG. 2, includes a plurality of data fields [0042] 111, 113, 115 and a bar code data field 117. Input form document 110 is fed into automatic feeder 22 and the feed control detection 24 determines when the entire document has been input. After correcting for imagery positioning in imagery positioning unit 28, an image of the scanned input document is shown on display 84. The display of the scanned image is graphically shown as scanned image 110 a in FIG. 2. To identify the useful data from other information on scanned image 110 a, the operator provides positional information (e.g., by moving a cursor via pointer 88) by locating data image fields 111 and 113 in relation to a recognized point on the scanned image (e.g., a comer edge or cross-hair mark on the image). Further, the size of the data field is altered by the operator (via pointer 88) in conjunction with data field 113 as shown by the broken lines about data field 113 and particularly arrow 114. The size and positional information for the data fields 115 and 117 have not been completed by the operator in FIG. 2. Position and size function 116 illustrates this feature. Alternatively, the operator may input a simple topographical description including field descriptors to “set-up” a form document. The operator may simply input “bottom 25% of scanned document” to identify a positional information of the data field image and select a data type “bar code.” This alternative inputs the topographical description of the data fields without utilizing a scanned input from the form document.
  • Data select function [0043] 120 enables the operator to select the type of data for each data field. See Coded Data Table above. Step 140 enables the operator to set the presence or absence of data validation parameters and the presence or absence of data error reporting and data correction. For example, data field 111 has been designated as an “alphabetic” character “case insensitive” field. Field 115 has been designated as an “optical marker” data type and the “check” is converted from an optical tick to a digital value “01.”The data descriptor for an optical marker also includes a data output configuration or format. Data field 113 has been classified as to a position subsequent to optical tick data field 115. Data field 117 has been characterized as a bar code information.
  • Step [0044] 150 enables the operator to select the output sequence for the data obtained, extracted and decoded in each data field. The output sequence selected in the illustrated embodiment is field 111, field 115, field 113 , field 117 and thereafter followed by delimiting characters CR-LF (carriage return, line feed). As such, the extracted and decoded data from input form document 110 would include an alphabetic character or character string in the first position, a digital value for the optical tick in the second position, a numeric character string in the third position, decoded bar code information in the fourth string, followed by delimiting characters CR-LF. Other delimiting characters may be utilized. Delimiting characters indicate the separation between records or separation between each input document.
  • In use, scanner system [0045] 10 stores a plurality of scanned form documents, each having unique data field descriptors. The data field descriptors include positional information for each data field unique to that form (i.e., relative position to another scannable and identifiable image point), data field size information, data type information, the presence or absence of data validation parameters, the presence or absence of data error reporting and data correction routines, and data output destination information. It may not be necessary for the system 10 to automatically correct or validate decoded data. Hence, data validation parameters and data error reporting and data correction parameters may be omitted. Once a plurality of form documents, represented by at least one data image field for each form document (and preferably a plurality of data image fields and corresponding data field descriptors for each form document) is stored in forms database 42, full operational performance of document scanner 10 can be achieved.
  • FIG. 3 diagrammatically shows the processing of a document which has imprinted data thereon. In the illustrated embodiment, document [0046] 110 operates not only as the input form document (see FIG. 2) but also the input document carrying imprinted data thereon which will be scanned by system 10. Similar numerals designate similar items throughout the specification.
  • Input document [0047] 110 is fed into automatic document feeder and scanning mechanism 22 (FIG. 1) and feed control double and chain detector 24 determines the edges of the document. Deskewing and noise reduction unit 26 enables image registering unit 28 to rotate the scanned image of the document as necessary. Optionally, scanner system 10 can imprint bar codes, numbers, letters, pictures, etc. via optional imprinting unit 30 on the documents before they reach the paper out stage 32. Optional image output module 34 configures the scanned image (e.g., as a TIFF file) and optionally ads bar codes, numbers, letters, pictures, etc. to the image and sends that output to optional output port 17. The scanned image may be part of the delimited character string. After the scanned image has been rotated to the correct point, form processing unit 40 compares various field descriptors from stored forms in forms database 42 with the scanned document image. Most likely, positional information for selected data fields from each of the plurality of stored forms is compared against the scanned image. Upon a reasonable match between positional locations and data types in those locations, a single form is selected from the database. Further, if one data field such as data field 111 in FIG. 3 is rotated or askew, shown by broken lines 111 a in FIG. 3, field extraction unit 46 realigns that data image field.
  • After one of the plurality of forms is selected, the data from each data field in the scanned document image is extracted via field extraction unit [0048] 46. In another words, the image from data fields 111, 113, 115 and 117 is extracted from scanned image document 110 a. In data field recognition unit 48, each field is analyzed using a proper algorithm for each data type. As stated earlier, each data field has a plurality of data field descriptors which include positional information, size information and data type information. The data type information correlates the data field image with one library in the collection of recognition library sets. Some of those recognition sets are shown as recognition engines 50 in FIG. 1. For example, an OCR library decodes and deciphers alphanumeric and typographic symbols in a data field image.
  • After the data images in each data field have been decoded based on field recognition [0049] 48 and recognition engine 50, the data fields are configured in separate files or storage areas shown in steps 202 and 204 in FIG. 3. After recognition, shown in step 204 in FIG. 3, the optical checks in data field115 have been converted from optical characters into digital format 01.
  • In data processing unit [0050] 60, each field undergoes a validation process if the operator has selected a data validation parameter during the input form sequence. For example, alphabetic fields may be subjected to a spell checker via a dictionary database 64. Mathematic or numeric data fields (see data fields 115 and 113) may be subject to mathematic algorithms. As an example of a numeric validation, the value in data field 115 must be either 01 or 10. It would be improper or an error if 00 were decoded or 11 were decoded indicating that the user who “checked the box” in data field 115 double checked the box or did not leave any optical marking in one of the two boxes. Logical check unit 68 enables the automatic check of these decoded data fields as established by the operator during creation of the form document.
  • Any error reports from field and rule checker unit [0051] 62 are supplied via control unit 80 to display 84. The operator at keyboard 86 may correct the error if the data correction field descriptor has been turn ON. If the operator is enabled to correct the data and does correct the error, summation module 64 substitutes the corrected data for the previously scanned and decoded incorrect data. Output step data formatting module 66 takes the individual files or data elements for fields 111, 115, 113 and 117 and puts them into a delimited string of decoded characters as shown by step 206. The string is output via port 15 to a further computer device. It should be appreciated that the further computer device can easily process this delimited string of decoded characters into a spreadsheet, database or any other type of word processing program.
  • The claims appended hereto are meant to cover modifications and changes within the scope and spirit of the present invention.[0052]

Claims (16)

    What is claimed is:
  1. 1. A method for scanning a document imprinted with data, locating the data and deciphering the data and outputting the data as a delimited string of decoded or calculated characters to a computer system via a common computer communications link, the method comprising:
    one of (a) scanning a form document that is adapted to have imprinted thereon data in at least one data image field and obtaining positional information for said at least one data image field on said form document or (b) inputting a topological description for said at least one data image field for said form document, said topological description including positional information for said at least one data field;
    identifying and storing data field descriptors for said at least one data field, said data field descriptors including said positional information and data field size information, data type information, the presence or absence of data validation parameters, the presence or absence of data error reporting and data correction, and data output destination information relative to said delimited string of decoded characters;
    with respect to other form documents, repeating the steps of scanning said other form documents or inputting topological descriptions of said other form documents and repeating the steps of identifying and storing said data field descriptors for each said form;
    scanning said document imprinted with data and capturing an image thereof as a scanned image;
    comparing said scanned image with said stored data descriptors for said forms, and utilizing positional, data field size and data type information, selecting one form corresponding to said scanned image;
    extracting data from said scanned image and decoding, calculating or and validating said data with decoding, calculation or validation routines, based upon said data field descriptors and storing the decoded data;
    reporting and correcting errors in the presence of said data error reporting and correction descriptor;
    outputting said decoded data as said delimited string of decoded characters based upon said data output destination information.
  2. 2. The method as claimed in claim 1 including the steps of displaying data that does not pass the validating step in the extracting, decoding and validating process and accepting an operator input with corrected data.
  3. 3. A method as claimed in claim 1 wherein said document bearing imprinted data includes a plurality imprinted data in a plurality of data fields, the method including repeating said step of identifying and storing data field descriptors for each data field of said plurality of data fields and the step of outputting includes outputting a plurality of decoded and validated data corresponding to said plurality of data into said delimited string of decoded characters.
  4. 4. A method as claimed in claim 1 wherein said data type includes data types including printed letters, printed numbers, optical marks, optical tick marks, optical cross-out marks, handwritten characters, bar codes and special optical characters and the step of decoding includes ascertaining whether the extracted data matches a stored data type character set..
  5. 5. A method as claimed in claim 1 wherein the step of extracting data from said scanned image includes extracting field images from said scanned image, said field image containing data images and the step extracting includes the steps of deskewing and attenuating smudges in said data fields by noise reduction techniques.
  6. 6. A method as claimed in claim 1 wherein all the steps are carried out in a single machine.
  7. 7. A method as claimed in claim 2 wherein said document bearing imprinted data includes a plurality imprinted data in a plurality of data fields, the method including repeating said step of identifying and storing data field descriptors for each data field of said plurality of data fields and the step of outputting includes outputting a plurality of decoded and validated data corresponding to said plurality of data into said delimited string of decoded characters.
  8. 8. A method as claimed in claim 7 wherein said data type includes data types including printed letters, printed numbers, optical marks, optical tick marks, optical cross-out marks, handwritten characters, bar codes and special optical characters and the step of decoding includes ascertaining whether the extracted data matches a stored data type character set..
  9. 9. A method as claimed in claim 8 wherein the step of extracting data from said scanned image includes extracting field images from said scanned image, said field image containing data images and the step extracting includes the steps of deskewing and attenuating smudges in said data fields by noise reduction techniques.
  10. 10. A method as claimed in claim 9 wherein all the steps are carried out in a single machine.
  11. 11. A unitary, stand-alone system for scanning, extracting and decoding a document imprinted with data, based upon a plurality of form documents, each form document having at least one data image field therein, the system outputting the data as a delimited string of decoded or calculated characters to a further computer system via a common computer communications link, the system comprising:
    a scanner for scanning said document imprinted with data and capturing an image thereof as a scanned image and for scanning said form document;
    a form input system, coupled to said scanner, having means for obtaining positional information for said at least one data image field on some form documents of said plurality of form documents and means for inputting a topological description for said at least one data image field for other forms of said plurality of form documents, said topological description including positional information for said at least one data field;
    means for identifying and storing data field descriptors for said at least one data field for each form document, said data field descriptors including said positional information and data field size information, data type information, the presence or absence of data validation parameters, the presence or absence of data error reporting and data correction, and data output destination information relative to said delimited string of decoded or calculated characters;
    selection system for selecting one form of said plurality of form documents corresponding to said scanned image based upon a comparison of said scanned image with said stored data descriptors for said forms, and utilizing positional, data field size and data type information;
    data extractor for obtaining data from said scanned image;
    data decoder for decoding the scanned data, said data decoder having a data validator to ascertain data validity in the presence of data validation parameters;
    data correction routine to correct errors in the decoded data in the presence of said data error reporting and correction descriptor;
    compiler for outputting said decoded data as said delimited string of decoded characters based upon said data output destination information.
  12. 12. A system as claimed in claim 11 wherein the system includes an operator interface including a display system and a data and command input system, said means for identifying coupled to said operator interface, and said operator interface providing some data field descriptors such as data type information, data field size information, and data validation parameters.
  13. 13. A system as claimed in claim 11 wherein said data correction routine is coupled to said operator interface, said data correction routine displaying data errors on said display and said operator interface adapted to accept operator input via said data and command input system to correct said scanned and decoded data.
  14. 14. A system as claimed in claim 11 including a deskewing system to reposition said scanned data from said document and a noise reduction system to diminish the adverse affects of smudges on said document imprinted with data.
  15. 15. A system as claimed in claim 12 wherein said data correction routine is coupled to said operator interface, said data correction routine displaying data errors on said display and said operator interface adapted to accept operator input via said data and command input system to correct said scanned and decoded data.
  16. 16. A system as claimed in claim 15 including a deskewing system to reposition said scanned data from said document and a noise reduction system to diminish the adverse affects of smudges on said document imprinted with data.
US09804272 2001-03-12 2001-03-12 Document scanner, system and method Expired - Fee Related US6782144B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US09804272 US6782144B2 (en) 2001-03-12 2001-03-12 Document scanner, system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US09804272 US6782144B2 (en) 2001-03-12 2001-03-12 Document scanner, system and method

Publications (2)

Publication Number Publication Date
US20020141660A1 true true US20020141660A1 (en) 2002-10-03
US6782144B2 US6782144B2 (en) 2004-08-24

Family

ID=25188580

Family Applications (1)

Application Number Title Priority Date Filing Date
US09804272 Expired - Fee Related US6782144B2 (en) 2001-03-12 2001-03-12 Document scanner, system and method

Country Status (1)

Country Link
US (1) US6782144B2 (en)

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030065593A1 (en) * 2001-10-01 2003-04-03 Masako Tabei Business activity control system
US20030108243A1 (en) * 1999-12-02 2003-06-12 Didier Charpentier Adaptive technology for automatic document analysis
WO2005029392A1 (en) * 2003-09-15 2005-03-31 Oce Document Technologies Gmbh Method and system for collecting data from a plurality of machine readable documents
WO2005043452A1 (en) * 2003-09-30 2005-05-12 Oce Document Technologies Gmbh Method and system for acquiring data from machine-readable documents
US20060010116A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060010115A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060008113A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060008114A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060184522A1 (en) * 2005-02-15 2006-08-17 Mcfarland Max E Systems and methods for generating and processing evolutionary documents
US20060285749A1 (en) * 2005-06-17 2006-12-21 Microsoft Corporation User-initiated reporting of handwriting recognition errors over the internet
WO2007006687A1 (en) * 2005-07-08 2007-01-18 Oce Document Technologies Gmbh Method, system and computer program product for transmitting data from a document application to a data application
US20070076240A1 (en) * 2005-10-04 2007-04-05 Kabushiki Kaisha Toshiba Image processing system
US20070089049A1 (en) * 2005-09-08 2007-04-19 Gormish Michael J Non-symbolic data system for the automated completion of forms
US20070133876A1 (en) * 2005-12-14 2007-06-14 Nokia Corporation Device, method, and computer program product for enhancing the use of electronic forms in mobile devices
US20080152209A1 (en) * 2006-12-21 2008-06-26 Bottomline Technologies (De) Inc. Electronic transaction processing server with automated transaction evaluation
US20090144188A1 (en) * 2007-11-29 2009-06-04 Finance And Compliance Solutions Apparatus, system and computer program product for a paperless credit application process
US20100097640A1 (en) * 2008-10-22 2010-04-22 Samsung Electronics Co., Ltd Image scanning apparatus and method thereof
US20110075939A1 (en) * 2009-09-25 2011-03-31 Getac Technology Corporation Data processing device using image as data source and data imput method through capturing image
US20110170788A1 (en) * 2010-01-12 2011-07-14 Grigori Nepomniachtchi Method for capturing data from mobile and scanned images of business cards
WO2012143948A3 (en) * 2011-04-18 2013-01-03 Jeswill Hitech Solutions Pvt. Ltd. Method and apparatus for processing content written in an application form using an e-pen
US20130156291A1 (en) * 2011-12-15 2013-06-20 Darryl S. O'Neill Methods of operating an image-based check processing system to detect a double feed condition of checks and an apparatus therefor
EP2450830A3 (en) * 2010-11-06 2013-08-07 Michael Marquardt Expiry date detection
US20130339102A1 (en) * 2012-06-14 2013-12-19 The One Page Company Inc. Proposal evaluation system
US20140198350A1 (en) * 2012-01-27 2014-07-17 Xerox Corporation Methods and systems for handling multiple documents while scanning
US20150170378A1 (en) * 2013-12-16 2015-06-18 Symbol Technologies, Inc. Method and apparatus for dimensioning box object
US20150178855A1 (en) * 2002-01-22 2015-06-25 Lavante, Inc. Ocr enabled management of accounts payable and/or accounts receivable auditing data
US9594740B1 (en) * 2016-06-21 2017-03-14 International Business Machines Corporation Forms processing system

Families Citing this family (64)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6883168B1 (en) 2000-06-21 2005-04-19 Microsoft Corporation Methods, systems, architectures and data structures for delivering software via a network
US7000230B1 (en) 2000-06-21 2006-02-14 Microsoft Corporation Network-based software extensions
US7624356B1 (en) 2000-06-21 2009-11-24 Microsoft Corporation Task-sensitive methods and systems for displaying command sets
US6948135B1 (en) 2000-06-21 2005-09-20 Microsoft Corporation Method and systems of providing information to computer users
US7191394B1 (en) 2000-06-21 2007-03-13 Microsoft Corporation Authoring arbitrary XML documents using DHTML and XSLT
US7346848B1 (en) 2000-06-21 2008-03-18 Microsoft Corporation Single window navigation methods and systems
US7155667B1 (en) 2000-06-21 2006-12-26 Microsoft Corporation User interface for integrated spreadsheets and word processing tables
US6912308B2 (en) * 2000-12-01 2005-06-28 Targus Communications Corp. Apparatus and method for automatic form recognition and pagination
US7392287B2 (en) * 2001-03-27 2008-06-24 Hemisphere Ii Investment Lp Method and apparatus for sharing information using a handheld device
US7013029B2 (en) * 2001-06-29 2006-03-14 Intel Corporation Incorporating handwritten notations into an electronic document
US20030004991A1 (en) * 2001-06-29 2003-01-02 Keskar Dhananjay V. Correlating handwritten annotations to a document
JP2003141528A (en) * 2001-10-29 2003-05-16 Tokuwa System Kk Figure information digitizing system
US7120299B2 (en) 2001-12-28 2006-10-10 Intel Corporation Recognizing commands written onto a medium
JP4181892B2 (en) * 2003-02-21 2008-11-19 キヤノン株式会社 Image processing method
US7415672B1 (en) 2003-03-24 2008-08-19 Microsoft Corporation System and method for designing electronic forms
US7275216B2 (en) 2003-03-24 2007-09-25 Microsoft Corporation System and method for designing electronic forms and hierarchical schemas
US7370066B1 (en) 2003-03-24 2008-05-06 Microsoft Corporation System and method for offline editing of data files
US7913159B2 (en) 2003-03-28 2011-03-22 Microsoft Corporation System and method for real-time validation of structured data files
US7296017B2 (en) 2003-03-28 2007-11-13 Microsoft Corporation Validation of XML data files
US7451392B1 (en) 2003-06-30 2008-11-11 Microsoft Corporation Rendering an HTML electronic form by applying XSLT to XML using a solution
US7406660B1 (en) 2003-08-01 2008-07-29 Microsoft Corporation Mapping between structured data and a visual surface
US7334187B1 (en) 2003-08-06 2008-02-19 Microsoft Corporation Electronic form aggregation
US7496560B2 (en) * 2003-09-23 2009-02-24 Amazon Technologies, Inc. Personalized searchable library with highlighting capabilities
EP1671235A4 (en) * 2003-09-23 2007-10-24 Amazon Com Inc Personalized searchable library with highlighting capabilities and access to electronic images of text based on user ownership of corresponding physical text
US7149353B2 (en) * 2003-09-23 2006-12-12 Amazon.Com, Inc. Method and system for suppression of features in digital images of content
US8819072B1 (en) 2004-02-02 2014-08-26 Microsoft Corporation Promoting data from structured data files
US8620083B2 (en) * 2004-12-03 2013-12-31 Google Inc. Method and system for character recognition
US7707039B2 (en) * 2004-02-15 2010-04-27 Exbiblio B.V. Automatic modification of web pages
US7496837B1 (en) 2004-04-29 2009-02-24 Microsoft Corporation Structural editing with schema awareness
US7774620B1 (en) 2004-05-27 2010-08-10 Microsoft Corporation Executing applications at appropriate trust levels
US7712022B2 (en) 2004-11-15 2010-05-04 Microsoft Corporation Mutually exclusive options in electronic forms
US7509353B2 (en) * 2004-11-16 2009-03-24 Microsoft Corporation Methods and systems for exchanging and rendering forms
US7721190B2 (en) 2004-11-16 2010-05-18 Microsoft Corporation Methods and systems for server side form processing
US7904801B2 (en) 2004-12-15 2011-03-08 Microsoft Corporation Recursive sections in electronic forms
US7937651B2 (en) 2005-01-14 2011-05-03 Microsoft Corporation Structural editing operations for network forms
US7548641B2 (en) * 2005-02-17 2009-06-16 Vectorsgi, Inc. System and method for embedding check data in a check image
US7447347B2 (en) * 2005-02-17 2008-11-04 Vectorsgi, Inc. Method and system for retaining MICR code format
US7725834B2 (en) 2005-03-04 2010-05-25 Microsoft Corporation Designer-created aspect for an electronic form template
US8200975B2 (en) 2005-06-29 2012-06-12 Microsoft Corporation Digital signatures for network forms
US8001459B2 (en) 2005-12-05 2011-08-16 Microsoft Corporation Enabling electronic documents for limited-capability computing devices
US7939176B2 (en) 2005-12-23 2011-05-10 Xerox Corporation Coated substrates and method of coating
CN101317148B (en) * 2005-12-30 2010-09-29 国际商业机器公司 Hand-written input method and apparatus based on video
US20070168382A1 (en) * 2006-01-03 2007-07-19 Michael Tillberg Document analysis system for integration of paper records into a searchable electronic database
US20070290053A1 (en) * 2006-06-15 2007-12-20 Xerox Corporation Pre-processing cleaning of pre-printed documents
JP4539613B2 (en) * 2006-06-28 2010-09-08 富士ゼロックス株式会社 Image forming apparatus, an image generating method and a program
US7424262B2 (en) * 2006-09-29 2008-09-09 Xerox Corporation Surface treatment of coated media
JP4914185B2 (en) * 2006-11-20 2012-04-11 株式会社Pfu Image reading apparatus and image reading processing method
US8155444B2 (en) * 2007-01-15 2012-04-10 Microsoft Corporation Image text to character information conversion
US8108764B2 (en) * 2007-10-03 2012-01-31 Esker, Inc. Document recognition using static and variable strings to create a document signature
US8639033B2 (en) * 2007-10-30 2014-01-28 Perot Systems Corporation System and method for viewing and utilizing data from electronic images
US7970328B2 (en) * 2007-11-16 2011-06-28 Xerox Corporation System and method for preparing magnetic ink character recognition readable documents
US9110434B2 (en) * 2007-11-16 2015-08-18 Xerox Corporation System and method for pre-treating magnetic ink character recognition readable documents
US20090130396A1 (en) * 2007-11-16 2009-05-21 Xerox Corporation Method and system for use in preparing magnetic ink character recognition readable documents
US8067142B2 (en) * 2007-12-20 2011-11-29 Xerox Corporation Coating, system and method for conditioning prints
US20090226090A1 (en) * 2008-03-06 2009-09-10 Okita Kunio Information processing system, information processing apparatus, information processing method, and storage medium
US8818018B2 (en) 2009-01-24 2014-08-26 Hewlett-Packard Development Company, L.P. System and method for enhancing security printing
US20110205370A1 (en) * 2010-02-19 2011-08-25 Research In Motion Limited Method, device and system for image capture, processing and storage
US8393272B2 (en) 2010-05-17 2013-03-12 Xerox Corporation Print media cleaning system and method
US20120027246A1 (en) * 2010-07-29 2012-02-02 Intuit Inc. Technique for collecting income-tax information
US8317446B2 (en) 2010-07-31 2012-11-27 Xerox Corporation System and method for treating printed flexible book covers prior to binding
US9715625B2 (en) * 2012-01-27 2017-07-25 Recommind, Inc. Hierarchical information extraction using document segmentation and optical character recognition correction
US9430456B2 (en) 2012-08-10 2016-08-30 Transaxy Inc. System for entering data into a data processing system
US20140188756A1 (en) * 2013-01-03 2014-07-03 Xerox Corporation Systems and methods for automatic processing of forms using augmented reality
US8805125B1 (en) * 2013-06-28 2014-08-12 Google Inc. Comparing extracted card data using continuous scanning

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317646A (en) * 1992-03-24 1994-05-31 Xerox Corporation Automated method for creating templates in a forms recognition and processing system
US5966473A (en) * 1996-11-28 1999-10-12 International Business Machines Corporation Method and apparatus for recognizing a quadrilateral object contained in an input bitmap image
US6028970A (en) * 1997-10-14 2000-02-22 At&T Corp Method and apparatus for enhancing optical character recognition

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5392447A (en) 1992-01-10 1995-02-21 Eastman Kodak Compay Image-based electronic pocket organizer with integral scanning unit
US5243149A (en) 1992-04-10 1993-09-07 International Business Machines Corp. Method and apparatus for improving the paper interface to computing systems
US5499108C1 (en) 1992-07-29 2001-01-16 Primax Electronics Ltd Document-driven scanning input device communicating with a computer
US5761328A (en) 1995-05-22 1998-06-02 Solberg Creations, Inc. Computer automated system and method for converting source-documents bearing alphanumeric text relating to survey measurements
US5970170A (en) 1995-06-07 1999-10-19 Kodak Limited Character recognition system indentification of scanned and real time handwritten characters

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317646A (en) * 1992-03-24 1994-05-31 Xerox Corporation Automated method for creating templates in a forms recognition and processing system
US5966473A (en) * 1996-11-28 1999-10-12 International Business Machines Corporation Method and apparatus for recognizing a quadrilateral object contained in an input bitmap image
US6028970A (en) * 1997-10-14 2000-02-22 At&T Corp Method and apparatus for enhancing optical character recognition

Cited By (47)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030108243A1 (en) * 1999-12-02 2003-06-12 Didier Charpentier Adaptive technology for automatic document analysis
US6943923B2 (en) * 1999-12-02 2005-09-13 Itesoft S.A. Adaptive technology for automatic document analysis
US20030065593A1 (en) * 2001-10-01 2003-04-03 Masako Tabei Business activity control system
US20150178855A1 (en) * 2002-01-22 2015-06-25 Lavante, Inc. Ocr enabled management of accounts payable and/or accounts receivable auditing data
US7668372B2 (en) 2003-09-15 2010-02-23 Open Text Corporation Method and system for collecting data from a plurality of machine readable documents
WO2005029392A1 (en) * 2003-09-15 2005-03-31 Oce Document Technologies Gmbh Method and system for collecting data from a plurality of machine readable documents
US20070065011A1 (en) * 2003-09-15 2007-03-22 Matthias Schiehlen Method and system for collecting data from a plurality of machine readable documents
US8270721B2 (en) * 2003-09-30 2012-09-18 Open Text S.A. Method and system for acquiring data from machine-readable documents
US20100094888A1 (en) * 2003-09-30 2010-04-15 Matthias Schiehlen Method and system for acquiring data from machine-readable documents
WO2005043452A1 (en) * 2003-09-30 2005-05-12 Oce Document Technologies Gmbh Method and system for acquiring data from machine-readable documents
US20070201768A1 (en) * 2003-09-30 2007-08-30 Matthias Schiehlen Method And System For Acquiring Data From Machine-Readable Documents
US7596271B2 (en) * 2004-07-07 2009-09-29 Canon Kabushiki Kaisha Image processing system and image processing method
US7640269B2 (en) 2004-07-07 2009-12-29 Canon Kabushiki Kaisha Image processing system and image processing method
US20060008113A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US7860266B2 (en) 2004-07-07 2010-12-28 Canon Kabushiki Kaisha Image processing system and image processing method
US20060010115A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060008114A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US20060010116A1 (en) * 2004-07-07 2006-01-12 Canon Kabushiki Kaisha Image processing system and image processing method
US8154769B2 (en) * 2005-02-15 2012-04-10 Ricoh Co. Ltd Systems and methods for generating and processing evolutionary documents
US20060184522A1 (en) * 2005-02-15 2006-08-17 Mcfarland Max E Systems and methods for generating and processing evolutionary documents
US20060285749A1 (en) * 2005-06-17 2006-12-21 Microsoft Corporation User-initiated reporting of handwriting recognition errors over the internet
US8667410B2 (en) * 2005-07-08 2014-03-04 Open Text S.A. Method, system and computer program product for transmitting data from a document application to a data application
WO2007006687A1 (en) * 2005-07-08 2007-01-18 Oce Document Technologies Gmbh Method, system and computer program product for transmitting data from a document application to a data application
US20080195968A1 (en) * 2005-07-08 2008-08-14 Johannes Schacht Method, System and Computer Program Product For Transmitting Data From a Document Application to a Data Application
US20070089049A1 (en) * 2005-09-08 2007-04-19 Gormish Michael J Non-symbolic data system for the automated completion of forms
US8732570B2 (en) 2005-09-08 2014-05-20 Ricoh Co. Ltd. Non-symbolic data system for the automated completion of forms
US20070076240A1 (en) * 2005-10-04 2007-04-05 Kabushiki Kaisha Toshiba Image processing system
US20070133876A1 (en) * 2005-12-14 2007-06-14 Nokia Corporation Device, method, and computer program product for enhancing the use of electronic forms in mobile devices
US7711191B2 (en) * 2006-12-21 2010-05-04 Michael John Kosek Electronic transaction processing server with automated transaction evaluation
US20080152209A1 (en) * 2006-12-21 2008-06-26 Bottomline Technologies (De) Inc. Electronic transaction processing server with automated transaction evaluation
US20090144188A1 (en) * 2007-11-29 2009-06-04 Finance And Compliance Solutions Apparatus, system and computer program product for a paperless credit application process
US8804167B2 (en) * 2008-10-22 2014-08-12 Samsung Electronics Co., Ltd. Image scanning apparatus and method thereof
US20100097640A1 (en) * 2008-10-22 2010-04-22 Samsung Electronics Co., Ltd Image scanning apparatus and method thereof
US20110075939A1 (en) * 2009-09-25 2011-03-31 Getac Technology Corporation Data processing device using image as data source and data imput method through capturing image
US20110170788A1 (en) * 2010-01-12 2011-07-14 Grigori Nepomniachtchi Method for capturing data from mobile and scanned images of business cards
EP2450830A3 (en) * 2010-11-06 2013-08-07 Michael Marquardt Expiry date detection
WO2012143948A3 (en) * 2011-04-18 2013-01-03 Jeswill Hitech Solutions Pvt. Ltd. Method and apparatus for processing content written in an application form using an e-pen
US9229544B2 (en) 2011-04-18 2016-01-05 Jeswill Hitech Solutions Pvt. Ltd. Method and apparatus for processing content written in an application form using an e-pen
US20130156291A1 (en) * 2011-12-15 2013-06-20 Darryl S. O'Neill Methods of operating an image-based check processing system to detect a double feed condition of checks and an apparatus therefor
US8761487B2 (en) * 2011-12-15 2014-06-24 Ncr Corporation Methods of operating an image-based check processing system to detect a double feed condition of checks and an apparatus therefor
US20140198350A1 (en) * 2012-01-27 2014-07-17 Xerox Corporation Methods and systems for handling multiple documents while scanning
US8964239B2 (en) * 2012-01-27 2015-02-24 Xerox Corporation Methods and systems for handling multiple documents while scanning
US20130339102A1 (en) * 2012-06-14 2013-12-19 The One Page Company Inc. Proposal evaluation system
US9741134B2 (en) * 2013-12-16 2017-08-22 Symbol Technologies, Llc Method and apparatus for dimensioning box object
US20150170378A1 (en) * 2013-12-16 2015-06-18 Symbol Technologies, Inc. Method and apparatus for dimensioning box object
US9846691B1 (en) * 2016-06-21 2017-12-19 International Business Machines Corporation Forms processing method
US9594740B1 (en) * 2016-06-21 2017-03-14 International Business Machines Corporation Forms processing system

Also Published As

Publication number Publication date Type
US6782144B2 (en) 2004-08-24 grant

Similar Documents

Publication Publication Date Title
Marti et al. A full English sentence database for off-line handwriting recognition
Shamilian et al. A retargetable table reader
Spitz Determination of the script and language content of document images
Likforman-Sulem et al. A Hough based algorithm for extracting text lines in handwritten documents
Taylor et al. Extraction of data from preprinted forms
US7013309B2 (en) Method and apparatus for extracting anchorable information units from complex PDF documents
US5642435A (en) Structured document processing with lexical classes as context
US6360951B1 (en) Hand-held scanning system for heuristically organizing scanned information
US5307423A (en) Machine recognition of handwritten character strings such as postal zip codes or dollar amount on bank checks
US7349576B2 (en) Method, device and computer program for recognition of a handwritten character
US4813077A (en) Sales transaction record processing system and method
US5539841A (en) Method for comparing image sections to determine similarity therebetween
Yu et al. A generic system for form dropout
US4992650A (en) Method and apparatus for barcode recognition in a digital image
US6501864B1 (en) Data medium handling apparatus and data medium handling method
Fujisawa et al. Segmentation methods for character recognition: from segmentation to document structure analysis
US5625721A (en) Certifiable optical character recognition
US4201978A (en) Document processing system
US6681044B1 (en) Retrieval of cursive Chinese handwritten annotations based on radical model
US6151423A (en) Character recognition with document orientation determination
US5237627A (en) Noise tolerant optical character recognition system
US6870947B2 (en) Method of processing items in a check processing system and an apparatus therefor
US5119433A (en) Method and system for locating the amount field on a document
US5251273A (en) Data processing system and method for sequentially repairing character recognition errors for scanned images of document forms
US5748809A (en) Active area identification on a machine readable form using form landmarks

Legal Events

Date Code Title Description
FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

REMI Maintenance fee reminder mailed
LAPS Lapse for failure to pay maintenance fees
FP Expired due to failure to pay maintenance fee

Effective date: 20160824